Cover Image

Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Space

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Houjun, Murty, Shikhar, Manning, Christopher D., Csordás, Róbert
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language Neural and Evolutionary Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Do Language Models Use Their Depth Efficiently?
by: Csordás, Róbert, et al.
Published: (2025)

Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
by: Csordás, Róbert, et al.
Published: (2024)

MoEUT: Mixture-of-Experts Universal Transformers
by: Csordás, Róbert, et al.
Published: (2024)

MrT5: Dynamic Token Merging for Efficient Byte-level Language Models
by: Kallini, Julie, et al.
Published: (2024)

SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
by: Csordás, Róbert, et al.
Published: (2023)

Position as Probability: Self-Supervised Transformers that Think Past Their Training for Length Extrapolation
by: Lee, Philip Heejun
Published: (2025)

Parameter-Efficient Fine-Tuning of LLMs with Mixture of Space Experts
by: Zhang, Buze, et al.
Published: (2026)

Semantic Sections: An Atlas-Native Feature Ontology for Obstructed Representation Spaces
by: Javidnia, Hossein
Published: (2026)

A Transformer-based Neural Architecture Search Method
by: Wang, Shang, et al.
Published: (2025)

Instance Generation for Meta-Black-Box Optimization through Latent Space Reverse Engineering
by: Wang, Chen, et al.
Published: (2025)

Parallel Algorithms for Exact Enumeration of Deep Neural Network Activation Regions
by: Drammis, Sabrina, et al.
Published: (2024)

Fleet of Agents: Coordinated Problem Solving with Large Language Models
by: Klein, Lars, et al.
Published: (2024)

Parallelization of Non-linear State-Space Models: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling
by: Farsang, Mónika, et al.
Published: (2025)

Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Security
by: Qu, Youyang, et al.
Published: (2024)

When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges
by: Wang, Chao, et al.
Published: (2024)

Hyperbolic Fine-Tuning for Large Language Models
by: Yang, Menglin, et al.
Published: (2024)

CAPO: Cost-Aware Prompt Optimization
by: Zehle, Tom, et al.
Published: (2025)

W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Models
by: Wang, Shang
Published: (2025)

Topic Modelling Black Box Optimization
by: Akramov, Roman, et al.
Published: (2025)

Language Models Learn Universal Representations of Numbers and Here's Why You Should Care
by: Štefánik, Michal, et al.
Published: (2025)

Accelerating Training Speed of Tiny Recursive Models with Curriculum Guided Adaptive Recursion
by: Qasim, Kaleem Ullah, et al.
Published: (2025)

Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction
by: Parab, Aishni, et al.
Published: (2025)

LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers
by: Abhyankar, Nikhil, et al.
Published: (2025)

Benchmarking Randomized Optimization Algorithms on Binary, Permutation, and Combinatorial Problem Landscapes
by: Odeyemi, Jethro, et al.
Published: (2025)

GLU Attention Improve Transformer
by: Wang, Zehao
Published: (2025)

Elastic Architecture Search for Efficient Language Models
by: Wang, Shang
Published: (2025)

Large Language Models and Emergence: A Complex Systems Perspective
by: Krakauer, David C., et al.
Published: (2025)

Understanding Textual Emotion Through Emoji Prediction
by: Gordon, Ethan, et al.
Published: (2025)

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models
by: Liang, Haoyu, et al.
Published: (2025)

Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs
by: Bergsma, Shane, et al.
Published: (2025)

Comply: Learning Sentences with Complex Weights inspired by Fruit Fly Olfaction
by: Figueroa, Alexei, et al.
Published: (2025)

A Gauge Theory of Superposition: Toward a Sheaf-Theoretic Atlas of Neural Representations
by: Javidnia, Hossein
Published: (2026)

Interlocking-free Selective Rationalization Through Genetic-based Learning
by: Ruggeri, Federico, et al.
Published: (2024)

Evolutionary Multi-Objective Optimization of Large Language Model Prompts for Balancing Sentiments
by: Baumann, Jill, et al.
Published: (2024)

H-Node Attack and Defense in Large Language Models
by: Yocam, Eric, et al.
Published: (2026)

EvoGPT-f: An Evolutionary GPT Framework for Benchmarking Formal Math Languages
by: Mercer, Johnathan
Published: (2024)

Compute Allocation in Evolutionary Search: From Depth-Breadth to Multi-Armed Bandits
by: Xing, Sixue, et al.
Published: (2026)

Vector Policy Optimization: Training for Diversity Improves Test-Time Search
by: Bahlous-Boldi, Ryan, et al.
Published: (2026)

MAR: Efficient Large Language Models via Module-aware Architecture Refinement
by: Cai, Junhong, et al.
Published: (2026)

Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models
by: Petruzzellis, Flavio, et al.
Published: (2024)